diff --git a/vllm/v1/engine/llm_engine.py b/vllm/v1/engine/llm_engine.py index 016ed7438c5a2..1f49de67d7493 100644 --- a/vllm/v1/engine/llm_engine.py +++ b/vllm/v1/engine/llm_engine.py @@ -42,6 +42,7 @@ def __init__( use_cached_outputs: bool = False, multiprocess_mode: bool = False, ) -> None: + # TODO: Can we avoid this? self.model_config = vllm_config.model_config diff --git a/vllm/v1/executor/multiproc_executor.py b/vllm/v1/executor/multiproc_executor.py index 228da1d9e23ed..26308c642cdb0 100644 --- a/vllm/v1/executor/multiproc_executor.py +++ b/vllm/v1/executor/multiproc_executor.py @@ -389,7 +389,6 @@ class ResponseStatus(Enum): def worker_busy_loop(self): """Main busy loop for Multiprocessing Workers""" - while True: method, args, kwargs = self.rpc_broadcast_mq.dequeue()